Two lines Iranian license plate detection and recognition using subspace learning

License plate detection and recognition has become high-priority research because of its many applications such as electronic payment systems, traffic monitoring and security control. This subject is divided into 2 main parts: license plate detection and character recognition. Although, there have been many studies in detection, two lines license plates such as Iranian motorcycle is less studied. Detection of this kind of license plates is more complicated because of background clutter. In order to solve this problem, this paper uses vertical edge detection and template matching. The following step is character recognition. There are many challenges such as skew, pose variations, blurriness, being dirty, illumination changes and some other distortions in real scenes. Our approach uses subspace learning to have proper performance under these conditions. To show the efficiency of our approach, the database including 60101 digits images is collected and the recognition algorithm is tested on it.